Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
TypeScript apifyautomationcrawlercrawlingheadlessheadless-chromejavascriptnodejsnpmplaywrightpuppeteerscraperscrapingtypescriptweb-crawlerweb-crawlingweb-scraping
test: Add end-to-end test of AdaptivePlaywrightCrawler (#3003)
Jan Bucharcf72d7019b17
diff --git a/test/e2e/adaptive-playwright-default/actor/.actor/actor.json b/test/e2e/adaptive-playwright-default/actor/.actor/actor.jsonnew file mode 100644index 000000000..f7b6d2f5f--- /dev/null+++ b/test/e2e/adaptive-playwright-default/actor/.actor/actor.json@@ -0,0 +1,7 @@+{+ "actorSpecification": 1,+ "name": "test-adaptive-playwright-default",+ "version": "0.0",+ "buildTag": "latest",+ "env": null+}diff --git a/test/e2e/adaptive-playwright-default/actor/.gitignore b/test/e2e/adaptive-playwright-default/actor/.gitignorenew file mode 100644index 000000000..ced7cbfc5--- /dev/null+++ b/test/e2e/adaptive-playwright-default/actor/.gitignore@@ -0,0 +1,7 @@+.idea+.DS_Store+node_modules+package-lock.json+apify_storage+crawlee_storage+storagediff --git a/test/e2e/adaptive-playwright-default/actor/Dockerfile b/test/e2e/adaptive-playwright-default/actor/Dockerfilenew file mode 100644index 000000000..e079f1c7a--- /dev/null+++ b/test/e2e/adaptive-playwright-default/actor/Dockerfile@@ -0,0 +1,23 @@+FROM node:22 AS builder++COPY /packages ./packages+COPY /package*.json ./+RUN npm --quiet set progress=false \+ && npm install --only=prod --no-optional --no-audit \+ && npm update++FROM apify/actor-node-playwright-chrome:22-beta++RUN rm -r node_modules+COPY --from=builder /node_modules ./node_modules+COPY --from=builder /packages ./packages+COPY --from=builder /package*.json ./+COPY /.actor ./.actor+COPY /main.js ./++RUN echo "Installed NPM packages:" \+ && (npm list --only=prod --no-optional --all || true) \+ && echo "Node.js version:" \+ && node --version \+ && echo "NPM version:" \+ && npm --versiondiff --git a/test/e2e/adaptive-playwright-default/actor/main.js b/test/e2e/adaptive-playwright-default/actor/main.jsnew file mode 100644index 000000000..ecc894b08--- /dev/null+++ b/test/e2e/adaptive-playwright-default/actor/main.js@@ -0,0 +1,52 @@+import { Actor } from 'apify';+import { AdaptivePlaywrightCrawler } from '@crawlee/playwright';+import { LogLevel } from '@apify/log';++await Actor.init({+ storage:+ process.env.STORAGE_IMPLEMENTATION === 'LOCAL'+ ? new (await import('@apify/storage-local')).ApifyStorageLocal()+ : undefined,+});++const crawler = new AdaptivePlaywrightCrawler({+ // Override the comparator so that it ignores `requestHandlerMode`+ resultComparator: (resultA, resultB) => {+ if (resultA.datasetItems.length === 1 && resultB.datasetItems.length === 1) {+ const itemA = resultA.datasetItems[0].item;+ const itemB = resultB.datasetItems[0].item;++ if (itemA.url === itemB.url && itemA.heading === itemB.heading) {+ return 'equal';+ }+ }++ return 'different';+ },+ requestHandler: async (context) => {+ const { url } = context.request;++ const heading = (await context.querySelector('h1')).text();++ const requestHandlerMode = await (async () => {+ try {+ await context.page.title();+ return 'browser';+ } catch {+ return 'httpOnly';+ }+ })();++ await context.pushData({ url, heading, requestHandlerMode });++ await context.enqueueLinks({+ globs: ['**/next/examples/*'],+ });+ },+});++crawler.log.setLevel(LogLevel.DEBUG);++await crawler.run(['https://crawlee.dev/js/docs/next/examples/accept-user-input']);++await Actor.exit({ exit: Actor.isAtHome() });diff --git a/test/e2e/adaptive-playwright-default/actor/package.json b/test/e2e/adaptive-playwright-default/actor/package.jsonnew file mode 100644index 000000000..176cb65d5--- /dev/null+++ b/test/e2e/adaptive-playwright-default/actor/package.json@@ -0,0 +1,32 @@+{+ "name": "test-adaptive-playwright-default",+ "version": "0.0.1",+ "description": "Adaptive Playwright Test - Default",+ "dependencies": {+ "apify": "next",+ "@apify/storage-local": "^2.1.3",+ "@crawlee/basic": "file:./packages/basic-crawler",+ "@crawlee/browser": "file:./packages/browser-crawler",+ "@crawlee/browser-pool": "file:./packages/browser-pool",+ "@crawlee/core": "file:./packages/core",+ "@crawlee/memory-storage": "file:./packages/memory-storage",+ "@crawlee/playwright": "file:./packages/playwright-crawler",+ "@crawlee/types": "file:./packages/types",+ "@crawlee/utils": "file:./packages/utils",+ "playwright": "*"+ },+ "overrides": {+ "apify": {+ "@crawlee/core": "file:./packages/core",+ "@crawlee/utils": "file:./packages/utils"+ },+ "@apify/storage-local": {+ "better-sqlite3": "^11.10.0"+ }+ },+ "scripts": {+ "start": "node main.js"+ },+ "type": "module",+ "license": "ISC"+}diff --git a/test/e2e/adaptive-playwright-default/test.mjs b/test/e2e/adaptive-playwright-default/test.mjsnew file mode 100644index 000000000..5e6f662e2--- /dev/null+++ b/test/e2e/adaptive-playwright-default/test.mjs@@ -0,0 +1,19 @@+import { initialize, getActorTestDir, runActor, expect, validateDataset } from '../tools.mjs';++const testActorDirname = getActorTestDir(import.meta.url);+await initialize(testActorDirname);++const { datasetItems } = await runActor(testActorDirname, 16384);++await expect(datasetItems.length > 15, 'Number of dataset items');+await expect(validateDataset(datasetItems, ['url', 'heading', 'requestHandlerMode']), 'Dataset items validation');++await expect(+ datasetItems.filter((it) => it.requestHandlerMode === 'browser').length >= 1,+ 'The crawler should handle at least one request in the browser',+);++await expect(+ datasetItems.filter((it) => it.requestHandlerMode === 'httpOnly').length >= 5,+ 'The crawler should handle some requests in http-only mode',+);